OpenAIAuto-detectedGPT 3.5 Turbo 0125
GPT 3.5 Turbo 0125 is an OpenAI proprietary model, released 25 Jan 2024. Its best configuration ranks #607 of 372 on the BenchLeader Index at 35.5 ±4.9, in the lower half. It scores highest in human preference (37) and lowest in maths (27). At $0.750 per million tokens blended it is mid-priced. Last measured 2 Sept 2026.
- Blended price
- $0.750/M
- $0.500 in · $1.50 out
- Output speed
- –
- First answer
- –
- Context
- 16k
- Overall index36
- Reasoning28
- Coding28
- Maths27
- Human preference37
Versions
OpenAI has shipped 4 models under this name. Each is ranked on its own results; a newer version often has fewer results so far, which holds its index nearer the average until more arrive.
| Model | Released | Index | Rank |
|---|---|---|---|
| GPT-4 Turbo | 9 Apr 2024 | 41.1 | #508 |
| GPT 3.5 Turbo 0125this page | 25 Jan 2024 | 35.5 | #607 |
| GPT 3.5 Turbo 1106 | 6 Nov 2023 | 39.3 | #545 |
| GPT-3.5 Turbohigh | 21 Sept 2023 | – | – |
Benchmark results
One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | default | Source |
|---|---|---|
| GPQA Diamond | 27.2%#269 | Epoch AI Benchmarking Hub |
| LMArena Hard Prompts | 1228#289 | LMArena |
Coding
| Benchmark | default | Source |
|---|---|---|
| WeirdML | 3.5%#154 | WeirdML |
| LMArena Coding | 1275#277 | LMArena |
Maths
| Benchmark | default | Source |
|---|---|---|
| FrontierMath Tiers 1–3 | 0.0%#105 | Epoch AI Benchmarking Hub |
| OTIS Mock AIME | 2.2%#246 | Epoch AI Benchmarking Hub |
| MATH Level 5 | 11.6%#86 | Epoch AI Benchmarking Hub |
Human preference
| Benchmark | default | Source |
|---|---|---|
| LMArena Text | 1225#286 | LMArena |
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0007 | – | – |
| Summarise a 30-page report | 12,000 / 600 | $0.0069 | – | – |
| Code edit | 6,000 / 1,500 | $0.0053 | – | – |
| Agentic coding session | 60,000 / 4,000 | $0.036 | – | – |
| Structured extraction | 2,000 / 200 | $0.0013 | – | – |
See also
Data as of 10 Sept 2026. Compare with another model.